Enhanced background model employing object classification for improved background-foreground segmentation
First Claim
1. A method, comprising:
- retrieving a plurality of images from a location that is substantially stationary relative to a scene, each image of the plurality of images of said scene comprising a plurality of pixels;
obtaining a background model of said scene, wherein obtaining the background model comprises determining at least one probability distribution corresponding to pixels of each image of the plurality of images, the step of determining performed by using a model wherein at least some pixels in each image of the plurality of images are modeled as being dependent on other pixels, further wherein said background model comprises (i) a term representing a probability of a global state of the scene and (ii) a term representing a probability of pixel appearances conditioned to the global state of the scene, wherein the global state of the scene is other than a global motion state of the scene; and
providing two indications in said background model for moving objects, a first indication for objects that typically move independently relative to said scene and a second indication for objects that are typically stationary relative to said scene, wherein the background model further comprises an object classification process that modifies probability tables for relevant pixels of an image of the plurality of images of the background model to contain the second indication.
2 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus are disclosed for generating and maintaining enhanced background models for use in background-foreground segmentation. Background models are modified to contain an indication of objects that are typically stationary. Thereafter, if an object moves and has been previously identified as an object that is typically stationary, the object will not unnecessarily be identified as part of the foreground during background-foreground segmentation. In an exemplary implementation, moving objects are classified into two sets. A first set includes objects that typically move independently and a second set includes objects that are typically stationary. Generally, once an object is assigned to the second (stationary object) set, the object will remain in the background, even if the object is moved (normally, movement of the object would cause the object to become part of the foreground).
-
Citations
17 Claims
-
1. A method, comprising:
-
retrieving a plurality of images from a location that is substantially stationary relative to a scene, each image of the plurality of images of said scene comprising a plurality of pixels; obtaining a background model of said scene, wherein obtaining the background model comprises determining at least one probability distribution corresponding to pixels of each image of the plurality of images, the step of determining performed by using a model wherein at least some pixels in each image of the plurality of images are modeled as being dependent on other pixels, further wherein said background model comprises (i) a term representing a probability of a global state of the scene and (ii) a term representing a probability of pixel appearances conditioned to the global state of the scene, wherein the global state of the scene is other than a global motion state of the scene; and providing two indications in said background model for moving objects, a first indication for objects that typically move independently relative to said scene and a second indication for objects that are typically stationary relative to said scene, wherein the background model further comprises an object classification process that modifies probability tables for relevant pixels of an image of the plurality of images of the background model to contain the second indication. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system comprising:
-
a memory that stores computer-readable code; and a processor operatively coupled to said memory, said processor configured to implement said computer-readable code, said computer-readable code configured to; retrieve a plurality of images from a location that is substantially stationary relative to a scene, each image of the plurality of images of said scene comprising a plurality of pixels; obtain a background model of said scene, wherein obtaining the background model comprises determining at least one probability distribution corresponding to pixels of each image of the plurality of images, the step of determining performed by using a model wherein at least some pixels in each image of the plurality of images are modeled as being dependent on other pixels, further wherein said background model comprises (i) a term representing a probability of a global state of the scene and (ii) a term representing a probability of pixel appearances conditioned to the global state of the scene, wherein the global state of the scene is other than a global motion state of the scene; and provide two indications in said background model for moving objects, a first indication for objects that typically move independently relative to said scene and a second indication for objects that are typically stationary relative to said scene, wherein the background model further comprises an object classification process that modifies probability tables for relevant pixels of an image of the plurality of images of the background model to contain the second indication. - View Dependent Claims (9, 10, 11, 12, 13)
-
-
14. A computer-readable medium having computer-readable code embodied thereon, said computer-readable program code comprising:
-
a step to retrieve a plurality of images from a location that is substantially stationary relative to a scene, each image of the plurality of images of said scene comprising a plurality of pixels; a step to obtain a background model of said scene, wherein obtaining the background model comprises determining at least one probability distribution corresponding to pixels of each image of the plurality of images, the step of determining performed by using a model wherein at least some pixels in each image of the plurality of images are modeled as being dependent on other pixels, further wherein said background model comprises (i) a term representing a probability of a global state of the scene and (ii) a term representing a probability of pixel appearances conditioned to the global state of the scene, wherein the global state of the scene is other than a global motion state of the scene; and a step to provide two indications in said background model for moving objects, a first indication for objects that typically move independently relative to said scene and a second indication for objects that are typically stationary relative to said scene, wherein the background model further comprises an object classification process that modifies probability tables for relevant pixels of an image of the plurality of images of the background model to contain the second indication. - View Dependent Claims (15)
-
-
16. A method, comprising:
-
retrieving a plurality of images from a location that is substantially stationary relative to a scene, each image of the plurality of images of said scene comprising a plurality of pixels; obtaining a background model of said scene, wherein obtaining the background model comprises determining at least one probability distribution corresponding to pixels of each image of the plurality of images, the step of determining performed by using a model wherein at least some pixels in each image of the plurality of images are modeled as being dependent on other pixels, further wherein said background model comprises (i) a term representing a probability of a global state of the scene and (ii) a term representing a probability of pixel appearances conditioned to the global state of the scene, wherein the global state of the scene is other than a global motion state of the scene; and providing two indications in said background model for moving objects, a first indication for an object that typically moves independently relative to said scene and a second indication for an object that is an inanimate object relative to said scene, wherein the background model further comprises an object classification process that modifies probability tables for relevant pixels of an image of the plurality of images of the background model to contain the second indication. - View Dependent Claims (17)
-
Specification